Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/core

Pull perf/core improvements and fixes from Jiri Olsa:

  * Add support to accumulate hist periods (Namhyung Kim)
Signed-off-by: NJiri Olsa <jolsa@kernel.org>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

tools/perf/Documentation/perf-report.txt

@@ -111,7 +111,7 @@ OPTIONS
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in -F will be appended
@@ -163,6 +163,11 @@ OPTIONS
 
 	Default: fractal,0.5,callee,function.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires callchains are recorded.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off

tools/perf/Documentation/perf-top.txt

@@ -119,7 +119,7 @@ Default is to monitor all CPUS.
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in --field will be appended
@@ -161,6 +161,12 @@ Default is to monitor all CPUS.
 	Setup and enable call-graph (stack chain/backtrace) recording,
 	implies -g.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires -g/--call-graph option
+	enabled.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off

tools/perf/Makefile.perf

@@ -400,6 +400,7 @@ LIB_OBJS += $(OUTPUT)tests/hists_common.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
 LIB_OBJS += $(OUTPUT)tests/hists_filter.o
 LIB_OBJS += $(OUTPUT)tests/hists_output.o
+LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o
 LIB_OBJS += $(OUTPUT)tests/python-use.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o

tools/perf/builtin-annotate.c

@@ -65,12 +65,13 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0);
+	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
+				true);
 	if (he == NULL)
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 	return ret;
 }
 

tools/perf/builtin-diff.c

@@ -315,7 +315,7 @@ static int hists__add_entry(struct hists *hists,
 			    u64 weight, u64 transaction)
 {
 	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction) != NULL)
+			       transaction, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }

tools/perf/builtin-report.c

@@ -72,6 +72,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -85,156 +89,52 @@ static void report__inc_stats(struct report *rep, struct hist_entry *he)
 	 */
 	if (he->stat.nr_events == 1)
 		rep->nr_entries++;
-
-	/*
-	 * Only counts number of samples at this stage as it's more
-	 * natural to do it here and non-sample events are also
-	 * counted in perf_session_deliver_event().  The dump_trace
-	 * requires this info is ready before going to the output tree.
-	 */
-	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		he->hists->stats.nr_non_filtered_samples++;
 }
 
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
 
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
+	report__inc_stats(rep, he);
 
-	if (rep->hide_unresolved && !al->sym)
+	if (!ui__has_annotation())
 		return 0;
 
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
-	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
-	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
 		if (err)
 			goto out;
-	}
-
-	report__inc_stats(rep, he);
-
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
-}
-
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
 
-		err = -ENOMEM;
-
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
-			report__inc_stats(rep, he);
-		} else
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
 			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
-}
-
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
 
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
-
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
-
-	if (ui__has_annotation())
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
-	report__inc_stats(rep, he);
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
 
 out:
 	return err;
 }
 
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -243,6 +143,10 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -257,22 +161,23 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
 
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
 	return ret;
 }
 
@@ -329,6 +234,14 @@ static int report__setup_sample_type(struct report *rep)
 			}
 	}
 
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!is_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
@@ -712,6 +625,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
 		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -804,8 +719,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack)
+	if (branch_mode == -1 && has_br_stack) {
 		sort__mode = SORT_MODE__BRANCH;
+		symbol_conf.cumulate_callchain = false;
+	}
 
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -813,6 +730,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
+		symbol_conf.cumulate_callchain = false;
 	}
 
 	if (setup_sorting() < 0) {

tools/perf/builtin-sched.c

@@ -1428,7 +1428,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	int err = 0;
 
 	evsel->hists.stats.total_period += sample->period;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;

tools/perf/builtin-top.c

@@ -196,6 +196,12 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 
 	pthread_mutex_unlock(&notes->lock);
 
+	/*
+	 * This function is now called with he->hists->lock held.
+	 * Release it before going to sleep.
+	 */
+	pthread_mutex_unlock(&he->hists->lock);
+
 	if (err == -ERANGE && !he->ms.map->erange_warned)
 		ui__warn_map_erange(he->ms.map, sym, ip);
 	else if (err == -ENOMEM) {
@@ -203,6 +209,8 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 		       sym->name);
 		sleep(1);
 	}
+
+	pthread_mutex_lock(&he->hists->lock);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -238,27 +246,6 @@ static void perf_top__show_details(struct perf_top *top)
 	pthread_mutex_unlock(&notes->lock);
 }
 
-static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
-						     struct addr_location *al,
-						     struct perf_sample *sample)
-{
-	struct hist_entry *he;
-
-	pthread_mutex_lock(&evsel->hists.lock);
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	pthread_mutex_unlock(&evsel->hists.lock);
-	if (he == NULL)
-		return NULL;
-
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-
-	return he;
-}
-
 static void perf_top__print_sym_table(struct perf_top *top)
 {
 	char bf[160];
@@ -662,6 +649,26 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	return 0;
 }
 
+static int hist_iter__top_callback(struct hist_entry_iter *iter,
+				   struct addr_location *al, bool single,
+				   void *arg)
+{
+	struct perf_top *top = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+
+	if (sort__has_sym && single) {
+		u64 ip = al->addr;
+
+		if (al->map)
+			ip = al->map->unmap_ip(al->map, ip);
+
+		perf_top__record_precise_ip(top, he, evsel->idx, ip);
+	}
+
+	return 0;
+}
+
 static void perf_event__process_sample(struct perf_tool *tool,
 				       const union perf_event *event,
 				       struct perf_evsel *evsel,
@@ -669,8 +676,6 @@ static void perf_event__process_sample(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
-	struct symbol *parent = NULL;
-	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 
@@ -745,25 +750,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
-		struct hist_entry *he;
+		struct hist_entry_iter iter = {
+			.add_entry_cb = hist_iter__top_callback,
+		};
 
-		err = sample__resolve_callchain(sample, &parent, evsel, &al,
-						top->max_stack);
-		if (err)
-			return;
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
 
-		he = perf_evsel__add_hist_entry(evsel, &al, sample);
-		if (he == NULL) {
-			pr_err("Problem incrementing symbol period, skipping event\n");
-			return;
-		}
+		pthread_mutex_lock(&evsel->hists.lock);
 
-		err = hist_entry__append_callchain(he, sample);
-		if (err)
-			return;
+		err = hist_entry_iter__add(&iter, &al, evsel, sample,
+					   top->max_stack, top);
+		if (err < 0)
+			pr_err("Problem incrementing symbol period, skipping event\n");
 
-		if (sort__has_sym)
-			perf_top__record_precise_ip(top, he, evsel->idx, ip);
+		pthread_mutex_unlock(&evsel->hists.lock);
 	}
 
 	return;
@@ -1001,6 +1004,10 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 
 	if (!strcmp(var, "top.call-graph"))
 		return record_parse_callchain(value, &top->record_opts);
+	if (!strcmp(var, "top.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -1095,6 +1102,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
 		     "mode[,dump_size]", record_callchain_help,
 		     &parse_callchain_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &top.max_stack,
 		    "Set the maximum stack depth when parsing the callchain. "
 		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
@@ -1200,6 +1209,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
 
+	if (!symbol_conf.use_callchain) {
+		symbol_conf.cumulate_callchain = false;
+		perf_hpp__cancel_cumulate();
+	}
+
 	symbol_conf.priv_size = sizeof(struct annotation);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);

tools/perf/tests/builtin-test.c

@@ -139,6 +139,10 @@ static struct test {
 		.desc = "Test output sorting of hist entries",
 		.func = test__hists_output,
 	},
+	{
+		.desc = "Test cumulation of child hist entries",
+		.func = test__hists_cumulate,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/tests/hists_common.c

@@ -12,9 +12,9 @@ static struct {
 	u32 pid;
 	const char *comm;
 } fake_threads[] = {
-	{ 100, "perf" },
-	{ 200, "perf" },
-	{ 300, "bash" },
+	{ FAKE_PID_PERF1, "perf" },
+	{ FAKE_PID_PERF2, "perf" },
+	{ FAKE_PID_BASH,  "bash" },
 };
 
 static struct {
@@ -22,15 +22,15 @@ static struct {
 	u64 start;
 	const char *filename;
 } fake_mmap_info[] = {
-	{ 100, 0x40000, "perf" },
-	{ 100, 0x50000, "libc" },
-	{ 100, 0xf0000, "[kernel]" },
-	{ 200, 0x40000, "perf" },
-	{ 200, 0x50000, "libc" },
-	{ 200, 0xf0000, "[kernel]" },
-	{ 300, 0x40000, "bash" },
-	{ 300, 0x50000, "libc" },
-	{ 300, 0xf0000, "[kernel]" },
+	{ FAKE_PID_PERF1, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF1, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF1, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_PERF2, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF2, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF2, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_BASH,  FAKE_MAP_BASH,   "bash" },
+	{ FAKE_PID_BASH,  FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_BASH,  FAKE_MAP_KERNEL, "[kernel]" },
 };
 
 struct fake_sym {
@@ -40,27 +40,30 @@ struct fake_sym {
 };
 
 static struct fake_sym perf_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "run_command" },
-	{ 900, 100, "cmd_record" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "run_command" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "cmd_record" },
 };
 
 static struct fake_sym bash_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "xmalloc" },
-	{ 900, 100, "xfree" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "xmalloc" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "xfree" },
 };
 
 static struct fake_sym libc_syms[] = {
 	{ 700, 100, "malloc" },
 	{ 800, 100, "free" },
 	{ 900, 100, "realloc" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "malloc" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "free" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "realloc" },
 };
 
 static struct fake_sym kernel_syms[] = {
-	{ 700, 100, "schedule" },
-	{ 800, 100, "page_fault" },
-	{ 900, 100, "sys_perf_event_open" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "schedule" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "page_fault" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "sys_perf_event_open" },
 };
 
 static struct {
@@ -102,7 +105,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 				.pid = fake_mmap_info[i].pid,
 				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
-				.len = 0x1000ULL,
+				.len = FAKE_MAP_LENGTH,
 				.pgoff = 0ULL,
 			},
 		};
@@ -193,10 +196,11 @@ void print_hists_out(struct hists *hists)
 		he = rb_entry(node, struct hist_entry, rb_node);
 
 		if (!he->filtered) {
-			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"\n",
+			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"/%"PRIu64"\n",
 				i, thread__comm_str(he->thread), he->thread->tid,
 				he->ms.map->dso->short_name,
-				he->ms.sym->name, he->stat.period);
+				he->ms.sym->name, he->stat.period,
+				he->stat_acc ? he->stat_acc->period : 0);
 		}
 
 		i++;

tools/perf/tests/hists_common.h

@@ -4,6 +4,34 @@
 struct machine;
 struct machines;
 
+#define FAKE_PID_PERF1  100
+#define FAKE_PID_PERF2  200
+#define FAKE_PID_BASH   300
+
+#define FAKE_MAP_PERF    0x400000
+#define FAKE_MAP_BASH    0x400000
+#define FAKE_MAP_LIBC    0x500000
+#define FAKE_MAP_KERNEL  0xf00000
+#define FAKE_MAP_LENGTH  0x100000
+
+#define FAKE_SYM_OFFSET1  700
+#define FAKE_SYM_OFFSET2  800
+#define FAKE_SYM_OFFSET3  900
+#define FAKE_SYM_LENGTH   100
+
+#define FAKE_IP_PERF_MAIN  FAKE_MAP_PERF + FAKE_SYM_OFFSET1
+#define FAKE_IP_PERF_RUN_COMMAND  FAKE_MAP_PERF + FAKE_SYM_OFFSET2
+#define FAKE_IP_PERF_CMD_RECORD  FAKE_MAP_PERF + FAKE_SYM_OFFSET3
+#define FAKE_IP_BASH_MAIN  FAKE_MAP_BASH + FAKE_SYM_OFFSET1
+#define FAKE_IP_BASH_XMALLOC  FAKE_MAP_BASH + FAKE_SYM_OFFSET2
+#define FAKE_IP_BASH_XFREE  FAKE_MAP_BASH + FAKE_SYM_OFFSET3
+#define FAKE_IP_LIBC_MALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET1
+#define FAKE_IP_LIBC_FREE  FAKE_MAP_LIBC + FAKE_SYM_OFFSET2
+#define FAKE_IP_LIBC_REALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET3
+#define FAKE_IP_KERNEL_SCHEDULE  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET1
+#define FAKE_IP_KERNEL_PAGE_FAULT  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET2
+#define FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET3
+
 /*
  * The setup_fake_machine() provides a test environment which consists
  * of 3 processes that have 3 mappings and in turn, have 3 symbols
@@ -13,7 +41,7 @@ struct machines;
  * .............  .............  ...................
  *    perf:  100           perf  main
  *    perf:  100           perf  run_command
- *    perf:  100           perf  comd_record
+ *    perf:  100           perf  cmd_record
  *    perf:  100           libc  malloc
  *    perf:  100           libc  free
  *    perf:  100           libc  realloc
@@ -22,7 +50,7 @@ struct machines;
  *    perf:  100       [kernel]  sys_perf_event_open
  *    perf:  200           perf  main
  *    perf:  200           perf  run_command
- *    perf:  200           perf  comd_record
+ *    perf:  200           perf  cmd_record
  *    perf:  200           libc  malloc
  *    perf:  200           libc  free
  *    perf:  200           libc  realloc

tools/perf/tests/hists_filter.c

@@ -21,33 +21,33 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .pid = 100, .ip = 0xf0000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .pid = 100, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [libc]   malloc() */
-	{ .pid = 100, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 	/* perf [perf]   main() */
-	{ .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* will be merged */
 	/* perf [perf]   cmd_record() */
-	{ .pid = 200, .ip = 0x40000 + 900, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* perf [kernel] page_fault() */
-	{ .pid = 200, .ip = 0xf0000 + 800, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	/* bash [bash]   main() */
-	{ .pid = 300, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
 	/* bash [bash]   xmalloc() */
-	{ .pid = 300, .ip = 0x40000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [libc]   malloc() */
-	{ .pid = 300, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
 	/* bash [kernel] page_fault() */
-	{ .pid = 300, .ip = 0xf0000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 };
 
-static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine __maybe_unused)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
-	struct hist_entry *he;
-	struct perf_sample sample = { .cpu = 0, };
+	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
 	/*
@@ -62,6 +62,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
 
 			/* make sure it has no filter at first */
 			evsel->hists.thread_filter = NULL;
@@ -76,18 +80,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 100, 1, 0);
-			if (he == NULL)
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0)
 				goto out;
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
 			fake_samples[i].sym = al.sym;
-
-			hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-			if (!he->filtered)
-				he->hists->stats.nr_non_filtered_samples++;
 		}
 	}
 

tools/perf/tests/hists_link.c

@@ -21,41 +21,41 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_common_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .pid = 100, .ip = 0xf0000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .pid = 200, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [perf]   cmd_record() */
-	{ .pid = 200, .ip = 0x40000 + 900, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* bash [bash]   xmalloc() */
-	{ .pid = 300, .ip = 0x40000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [libc]   malloc() */
-	{ .pid = 300, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
 };
 
 static struct sample fake_samples[][5] = {
 	{
 		/* perf [perf]   run_command() */
-		{ .pid = 100, .ip = 0x40000 + 800, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_RUN_COMMAND, },
 		/* perf [libc]   malloc() */
-		{ .pid = 100, .ip = 0x50000 + 700, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 		/* perf [kernel] page_fault() */
-		{ .pid = 100, .ip = 0xf0000 + 800, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 		/* perf [kernel] sys_perf_event_open() */
-		{ .pid = 200, .ip = 0xf0000 + 900, },
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, },
 		/* bash [libc]   free() */
-		{ .pid = 300, .ip = 0x50000 + 800, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_FREE, },
 	},
 	{
 		/* perf [libc]   free() */
-		{ .pid = 200, .ip = 0x50000 + 800, },
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_LIBC_FREE, },
 		/* bash [libc]   malloc() */
-		{ .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, }, /* will be merged */
 		/* bash [bash]   xfee() */
-		{ .pid = 300, .ip = 0x40000 + 900, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XFREE, },
 		/* bash [libc]   realloc() */
-		{ .pid = 300, .ip = 0x50000 + 900, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_REALLOC, },
 		/* bash [kernel] page_fault() */
-		{ .pid = 300, .ip = 0xf0000 + 800, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	},
 };
 
@@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	struct perf_evsel *evsel;
 	struct addr_location al;
 	struct hist_entry *he;
-	struct perf_sample sample = { .cpu = 0, };
+	struct perf_sample sample = { .period = 1, };
 	size_t i = 0, k;
 
 	/*
@@ -88,7 +88,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 
@@ -112,7 +112,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 

tools/perf/tests/hists_output.c

@@ -22,31 +22,31 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .cpu = 0, .pid = 100, .ip = 0xf0000 + 700, },
+	{ .cpu = 0, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 700, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [perf]   cmd_record() */
-	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 900, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* perf [libc]   malloc() */
-	{ .cpu = 1, .pid = 100, .ip = 0x50000 + 700, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 	/* perf [libc]   free() */
-	{ .cpu = 2, .pid = 100, .ip = 0x50000 + 800, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
 	/* perf [perf]   main() */
-	{ .cpu = 2, .pid = 200, .ip = 0x40000 + 700, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [kernel] page_fault() */
-	{ .cpu = 2, .pid = 200, .ip = 0xf0000 + 800, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	/* bash [bash]   main() */
-	{ .cpu = 3, .pid = 300, .ip = 0x40000 + 700, },
+	{ .cpu = 3, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
 	/* bash [bash]   xmalloc() */
-	{ .cpu = 0, .pid = 300, .ip = 0x40000 + 800, },
+	{ .cpu = 0, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [kernel] page_fault() */
-	{ .cpu = 1, .pid = 300, .ip = 0xf0000 + 800, },
+	{ .cpu = 1, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 };
 
 static int add_hist_entries(struct hists *hists, struct machine *machine)
 {
 	struct addr_location al;
-	struct hist_entry *he;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
@@ -56,6 +56,10 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 				.misc = PERF_RECORD_MISC_USER,
 			},
 		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
 
 		sample.cpu = fake_samples[i].cpu;
 		sample.pid = fake_samples[i].pid;
@@ -66,9 +70,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		he = __hists__add_entry(hists, &al, NULL, NULL, NULL,
-					sample.period, 1, 0);
-		if (he == NULL)
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
 			goto out;
 
 		fake_samples[i].thread = al.thread;

tools/perf/tests/tests.h

@@ -45,6 +45,7 @@ int test__hists_filter(void);
 int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
+int test__hists_cumulate(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT

tools/perf/ui/browsers/hists.c

@@ -37,7 +37,6 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
-					     struct hists *hists,
 					     float min_pcnt);
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
@@ -319,7 +318,7 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 	struct hists *hists = browser->hists;
 
 	for (nd = rb_first(&hists->entries);
-	     (nd = hists__filter_entries(nd, hists, browser->min_pcnt)) != NULL;
+	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
 	     nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		hist_entry__set_folding(he, unfold);
@@ -651,13 +650,36 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
 			  __hpp__slsmg_color_printf, true);		\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
+static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
+{									\
+	return he->stat_acc->_field;					\
+}									\
+									\
+static int								\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+				struct perf_hpp *hpp,			\
+				struct hist_entry *he)			\
+{									\
+	if (!symbol_conf.cumulate_callchain) {				\
+		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		slsmg_printf("%s", hpp->buf);				\
+									\
+		return ret;						\
+	}								\
+	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
+			  __hpp__slsmg_color_printf, true);		\
+}
+
 __HPP_COLOR_PERCENT_FN(overhead, period)
 __HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
 __HPP_COLOR_PERCENT_FN(overhead_us, period_us)
 __HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
 __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
 
 #undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
 
 void hist_browser__init_hpp(void)
 {
@@ -671,6 +693,8 @@ void hist_browser__init_hpp(void)
 				hist_browser__hpp_color_overhead_guest_sys;
 	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
 				hist_browser__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				hist_browser__hpp_color_overhead_acc;
 }
 
 static int hist_browser__show_entry(struct hist_browser *browser,
@@ -783,15 +807,12 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(h->hists);
-		float percent = 0.0;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
-		if (total)
-			percent = h->stat.period * 100.0 / total;
-
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < hb->min_pcnt)
 			continue;
 
@@ -804,16 +825,11 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 }
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
-					     struct hists *hists,
 					     float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(hists);
-		float percent = 0.0;
-
-		if (total)
-			percent = h->stat.period * 100.0 / total;
+		float percent = hist_entry__get_percent_limit(h);
 
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
@@ -825,16 +841,11 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 }
 
 static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
-						  struct hists *hists,
 						  float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(hists);
-		float percent = 0.0;
-
-		if (total)
-			percent = h->stat.period * 100.0 / total;
+		float percent = hist_entry__get_percent_limit(h);
 
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
@@ -863,14 +874,14 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 	switch (whence) {
 	case SEEK_SET:
 		nd = hists__filter_entries(rb_first(browser->entries),
-					   hb->hists, hb->min_pcnt);
+					   hb->min_pcnt);
 		break;
 	case SEEK_CUR:
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
 		nd = hists__filter_prev_entries(rb_last(browser->entries),
-						hb->hists, hb->min_pcnt);
+						hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -913,8 +924,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd), hb->hists,
-						   hb->min_pcnt);
+			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -947,7 +957,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd), hb->hists,
+			nd = hists__filter_prev_entries(rb_prev(nd),
 							hb->min_pcnt);
 			if (nd == NULL)
 				break;
@@ -1126,7 +1136,6 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 {
 	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
-						   browser->hists,
 						   browser->min_pcnt);
 	int printed = 0;
 
@@ -1134,8 +1143,7 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd), browser->hists,
-					   browser->min_pcnt);
+		nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
 	}
 
 	return printed;
@@ -1372,8 +1380,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 		return;
 	}
 
-	while ((nd = hists__filter_entries(nd, hb->hists,
-					   hb->min_pcnt)) != NULL) {
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		nr_entries++;
 		nd = rb_next(nd);
 	}

tools/perf/ui/gtk/hists.c

@@ -47,11 +47,26 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
 			  __percent_color_snprintf, true);			\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      __percent_color_snprintf, true);			\
+}
+
 __HPP_COLOR_PERCENT_FN(overhead, period)
 __HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
 __HPP_COLOR_PERCENT_FN(overhead_us, period_us)
 __HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
 __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
 
 #undef __HPP_COLOR_PERCENT_FN
 
@@ -68,6 +83,8 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_guest_sys;
 	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
 				perf_gtk__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				perf_gtk__hpp_color_overhead_acc;
 }
 
 static void callchain_list__sym_name(struct callchain_list *cl,
@@ -181,6 +198,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
+		/*
+		 * XXX no way to determine where symcol column is..
+		 *     Just use last column for now.
+		 */
+		if (perf_hpp__is_sort_entry(fmt))
+			sym_col = col_idx;
+
 		fmt->header(fmt, &hpp, hists_to_evsel(hists));
 
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
@@ -209,14 +233,12 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		GtkTreeIter iter;
 		u64 total = hists__total_period(h->hists);
-		float percent = 0.0;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
-		if (total)
-			percent = h->stat.period * 100.0 / total;
-
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < min_pcnt)
 			continue;
 
@@ -238,7 +260,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 		if (symbol_conf.use_callchain && sort__has_sym) {
 			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				total = h->stat.period;
+				total = symbol_conf.cumulate_callchain ?
+					h->stat_acc->period : h->stat.period;
 
 			perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
 						sym_col, total);

tools/perf/ui/hist.c

@@ -104,6 +104,18 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	return ret;
 }
 
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	if (!symbol_conf.cumulate_callchain) {
+		return snprintf(hpp->buf, hpp->size, "%*s",
+				fmt_percent ? 8 : 12, "N/A");
+	}
+
+	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+}
+
 static int field_cmp(u64 field_a, u64 field_b)
 {
 	if (field_a > field_b)
@@ -160,6 +172,24 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
 	return ret;
 }
 
+static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
+			   hpp_field_fn get_field)
+{
+	s64 ret = 0;
+
+	if (symbol_conf.cumulate_callchain) {
+		/*
+		 * Put caller above callee when they have equal period.
+		 */
+		ret = field_cmp(get_field(a), get_field(b));
+		if (ret)
+			return ret;
+
+		ret = b->callchain->max_depth - a->callchain->max_depth;
+	}
+	return ret;
+}
+
 #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
 static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
 			       struct perf_hpp *hpp,			\
@@ -242,6 +272,34 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 	return __hpp__sort(a, b, he_get_##_field);				\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      hpp_color_scnprintf, true);			\
+}
+
+#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
+			      hpp_entry_scnprintf, true);			\
+}
+
+#define __HPP_SORT_ACC_FN(_type, _field)					\
+static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+{										\
+	return __hpp__sort_acc(a, b, he_get_acc_##_field);			\
+}
+
 #define __HPP_ENTRY_RAW_FN(_type, _field)					\
 static u64 he_get_raw_##_field(struct hist_entry *he)				\
 {										\
@@ -270,18 +328,27 @@ __HPP_COLOR_PERCENT_FN(_type, _field)					\
 __HPP_ENTRY_PERCENT_FN(_type, _field)					\
 __HPP_SORT_FN(_type, _field)
 
+#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+__HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+__HPP_SORT_ACC_FN(_type, _field)
+
 #define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
 __HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
 __HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
+__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
 
 HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
 HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
 HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
 HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
 HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
+HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
 
 HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
 HPP_RAW_FNS(period, "Period", period, 12, 12)
@@ -303,6 +370,17 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 		.sort	= hpp__sort_ ## _name,		\
 	}
 
+#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _name,		\
+	}
+
 #define HPP__PRINT_FNS(_name)				\
 	{						\
 		.header	= hpp__header_ ## _name,	\
@@ -319,6 +397,7 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS(overhead_us),
 	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
 	HPP__COLOR_PRINT_FNS(overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
 	HPP__PRINT_FNS(samples),
 	HPP__PRINT_FNS(period)
 };
@@ -328,16 +407,23 @@ LIST_HEAD(perf_hpp__sort_list);
 
 
 #undef HPP__COLOR_PRINT_FNS
+#undef HPP__COLOR_ACC_PRINT_FNS
 #undef HPP__PRINT_FNS
 
 #undef HPP_PERCENT_FNS
+#undef HPP_PERCENT_ACC_FNS
 #undef HPP_RAW_FNS
 
 #undef __HPP_HEADER_FN
 #undef __HPP_WIDTH_FN
 #undef __HPP_COLOR_PERCENT_FN
 #undef __HPP_ENTRY_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
+#undef __HPP_ENTRY_ACC_PERCENT_FN
 #undef __HPP_ENTRY_RAW_FN
+#undef __HPP_SORT_FN
+#undef __HPP_SORT_ACC_FN
+#undef __HPP_SORT_RAW_FN
 
 
 void perf_hpp__init(void)
@@ -361,6 +447,13 @@ void perf_hpp__init(void)
 	if (field_order)
 		return;
 
+	if (symbol_conf.cumulate_callchain) {
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
+
+		perf_hpp__format[PERF_HPP__OVERHEAD].header =
+						hpp__header_overhead_self;
+	}
+
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 
 	if (symbol_conf.show_cpu_utilization) {
@@ -383,6 +476,12 @@ void perf_hpp__init(void)
 	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
 	if (list_empty(list))
 		list_add(list, &perf_hpp__sort_list);
+
+	if (symbol_conf.cumulate_callchain) {
+		list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
+		if (list_empty(list))
+			list_add(list, &perf_hpp__sort_list);
+	}
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -390,6 +489,11 @@ void perf_hpp__column_register(struct perf_hpp_fmt *format)
 	list_add_tail(&format->list, &perf_hpp__list);
 }
 
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+{
+	list_del(&format->list);
+}
+
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 {
 	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
@@ -401,6 +505,21 @@ void perf_hpp__column_enable(unsigned col)
 	perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
+void perf_hpp__column_disable(unsigned col)
+{
+	BUG_ON(col >= PERF_HPP__MAX_INDEX);
+	perf_hpp__column_unregister(&perf_hpp__format[col]);
+}
+
+void perf_hpp__cancel_cumulate(void)
+{
+	if (field_order)
+		return;
+
+	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
+	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+}
+
 void perf_hpp__setup_output_field(void)
 {
 	struct perf_hpp_fmt *fmt;

tools/perf/ui/stdio/hist.c

@@ -271,7 +271,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 {
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain, he->stat.period,
+		return callchain__fprintf_graph(fp, &he->sorted_chain,
+						symbol_conf.cumulate_callchain ?
+						he->stat_acc->period : he->stat.period,
 						left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
@@ -461,12 +463,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		float percent = h->stat.period * 100.0 /
-					hists->stats.total_period;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < min_pcnt)
 			continue;
 

tools/perf/util/callchain.c

@@ -616,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 	if (sample->callchain == NULL)
 		return 0;
 
-	if (symbol_conf.use_callchain || sort__has_parent) {
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+	    sort__has_parent) {
 		return machine__resolve_callchain(al->machine, evsel, al->thread,
 						  sample, parent, al, max_stack);
 	}
@@ -629,3 +630,45 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
 		return 0;
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved)
+{
+	al->map = node->map;
+	al->sym = node->sym;
+	if (node->map)
+		al->addr = node->map->map_ip(node->map, node->ip);
+	else
+		al->addr = node->ip;
+
+	if (al->sym == NULL) {
+		if (hide_unresolved)
+			return 0;
+		if (al->map == NULL)
+			goto out;
+	}
+
+	if (al->map->groups == &al->machine->kmaps) {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_KERNEL;
+			al->level = 'k';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+			al->level = 'g';
+		}
+	} else {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_USER;
+			al->level = '.';
+		} else if (perf_guest) {
+			al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+			al->level = 'u';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+			al->level = 'H';
+		}
+	}
+
+out:
+	return 1;
+}

tools/perf/util/callchain.h

@@ -162,7 +162,18 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 			      struct perf_evsel *evsel, struct addr_location *al,
 			      int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved);
 
 extern const char record_callchain_help[];
 int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+					     struct callchain_cursor *src)
+{
+	*dest = *src;
+
+	dest->first = src->curr;
+	dest->nr -= src->pos;
+}
 #endif	/* __PERF_CALLCHAIN_H */

tools/perf/util/hist.c

@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -231,6 +232,8 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 		return true;
 
 	he_stat__decay(&he->stat);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__decay(he->stat_acc);
 
 	diff = prev_period - he->stat.period;
 
@@ -276,14 +279,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+		callchain_size = sizeof(struct callchain_root);
+
+	he = zalloc(sizeof(*he) + callchain_size);
 
 	if (he != NULL) {
 		*he = *template;
 
+		if (symbol_conf.cumulate_callchain) {
+			he->stat_acc = malloc(sizeof(he->stat));
+			if (he->stat_acc == NULL) {
+				free(he);
+				return NULL;
+			}
+			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
+		}
+
 		if (he->ms.map)
 			he->ms.map->referenced = true;
 
@@ -295,6 +315,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				free(he->stat_acc);
 				free(he);
 				return NULL;
 			}
@@ -333,7 +354,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
 					 struct hist_entry *entry,
-					 struct addr_location *al)
+					 struct addr_location *al,
+					 bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -357,7 +379,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period, weight);
+			if (sample_self)
+				he_stat__add_period(&he->stat, period, weight);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_period(he->stat_acc, period, weight);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -385,14 +410,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
 		return NULL;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (sample_self)
+		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
 	return he;
 }
 
@@ -401,7 +429,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction)
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -426,7 +455,429 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al);
+	return add_hist_entry(hists, &entry, al, sample_self);
+}
+
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
+
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	iter->priv = mi;
+	return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
+
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0, true);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
+
+	iter->he = NULL;
+	return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
+
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
+
+	iter->priv = bi;
+	return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	/* to avoid calling callback function */
+	iter->he = NULL;
+
+	return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
+
+	if (bi == NULL)
+		return 0;
+
+	if (iter->curr >= iter->total)
+		return 0;
+
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
+
+	bi = iter->priv;
+
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 */
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+				1, 1, 0, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+
+	if (he == NULL)
+		return 0;
+
+	iter->he = NULL;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+			      struct addr_location *al __maybe_unused)
+{
+	struct hist_entry **he_cache;
+
+	callchain_cursor_commit(&callchain_cursor);
+
+	/*
+	 * This is for detecting cycles or recursions so that they're
+	 * cumulated only one time to prevent entries more than 100%
+	 * overhead.
+	 */
+	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	if (he_cache == NULL)
+		return -ENOMEM;
+
+	iter->priv = he_cache;
+	iter->curr = 0;
+
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+	/*
+	 * We need to re-initialize the cursor since callchain_append()
+	 * advanced the cursor to the end.
+	 */
+	callchain_cursor_commit(&callchain_cursor);
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
+{
+	struct callchain_cursor_node *node;
+
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
+
+	return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+			       struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	struct hist_entry he_tmp = {
+		.cpu = al->cpu,
+		.thread = al->thread,
+		.comm = thread__comm(al->thread),
+		.ip = al->addr,
+		.ms = {
+			.map = al->map,
+			.sym = al->sym,
+		},
+		.parent = iter->parent,
+	};
+	int i;
+	struct callchain_cursor cursor;
+
+	callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+	callchain_cursor_advance(&callchain_cursor);
+
+	/*
+	 * Check if there's duplicate entries in the callchain.
+	 * It's possible that it has cycles or recursive calls.
+	 */
+	for (i = 0; i < iter->curr; i++) {
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
+			return 0;
+		}
+	}
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &cursor, sample->period);
+	return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return 0;
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
+
+	iter->evsel = evsel;
+	iter->sample = sample;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
+
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
+
+	return err;
 }
 
 int64_t
@@ -469,6 +920,7 @@ void hist_entry__free(struct hist_entry *he)
 {
 	zfree(&he->branch_info);
 	zfree(&he->mem_info);
+	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free(he);
 }
@@ -494,6 +946,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 		if (!cmp) {
 			he_stat__add_stat(&iter->stat, &he->stat);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
@@ -800,6 +1254,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
 	events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
@@ -831,7 +1292,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(pair);
+	he = hist_entry__new(pair, true);
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;

tools/perf/util/hist.h

@@ -96,12 +96,50 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+	/* user-defined callback function (optional) */
+	int (*add_entry_cb)(struct hist_entry_iter *iter,
+			    struct addr_location *al, bool single, void *arg);
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction);
+				      u64 weight, u64 transaction,
+				      bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg);
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
@@ -119,6 +157,7 @@ u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
@@ -192,6 +231,7 @@ enum {
 	PERF_HPP__OVERHEAD_US,
 	PERF_HPP__OVERHEAD_GUEST_SYS,
 	PERF_HPP__OVERHEAD_GUEST_US,
+	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
 
@@ -200,7 +240,11 @@ enum {
 
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
 void perf_hpp__setup_output_field(void);
 void perf_hpp__reset_output_field(void);
@@ -218,6 +262,9 @@ typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	       hpp_field_fn get_field, const char *fmt,
 	       hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {

tools/perf/util/sort.c

@@ -1061,6 +1061,7 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
 };
@@ -1581,6 +1582,9 @@ void reset_output_field(void)
 	sort__has_sym = 0;
 	sort__has_dso = 0;
 
+	field_order = NULL;
+	sort_order = NULL;
+
 	reset_dimensions();
 	perf_hpp__reset_output_field();
 }

tools/perf/util/sort.h

@@ -20,7 +20,7 @@
 
 #include "parse-options.h"
 #include "parse-events.h"
-
+#include "hist.h"
 #include "thread.h"
 
 extern regex_t parent_regex;
@@ -82,6 +82,7 @@ struct hist_entry {
 		struct list_head head;
 	} pairs;
 	struct he_stat		stat;
+	struct he_stat		*stat_acc;
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
@@ -130,6 +131,21 @@ static inline void hist_entry__add_pair(struct hist_entry *pair,
 	list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
+
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,

tools/perf/util/symbol.c

@@ -29,11 +29,12 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
-	.use_modules	  = true,
-	.try_vmlinux_path = true,
-	.annotate_src	  = true,
-	.demangle	  = true,
-	.symfs            = "",
+	.use_modules		= true,
+	.try_vmlinux_path	= true,
+	.annotate_src		= true,
+	.demangle		= true,
+	.cumulate_callchain	= true,
+	.symfs			= "",
 };
 
 static enum dso_binary_type binary_type_symtab[] = {

tools/perf/util/symbol.h

@@ -109,6 +109,7 @@ struct symbol_conf {
 			show_nr_samples,
 			show_total_period,
 			use_callchain,
+			cumulate_callchain,
 			exclude_other,
 			show_cpu_utilization,
 			initialized,